Touchless multi-staged retail process automation systems and methods

Abstract

A touchless multi-staged retail process automation systems and methods (retail process automation system) to automate key store functionalities within retail stores is disclosed. The retail process automation system receives a set of commands (e.g., a voice command) to automatically perform retail store operations such as opening a store, closing a close, automatically opening tills, etc. with the single command. As a result, the retail process automation system replaces the multiple-touches required by conventional systems with a touchless solution, thereby providing increased time and resource efficiency of managing store operations. For example, the retail process automation system intercepts a voice command to identify the associated retail store information and source of the command. The retail process automation system then generates a set of operations associated with the received voice command to alter a state of the retail store.

We claim: 
     
       1. A computer system comprising:
 at least one hardware processor; and 
 at least one non-transitory memory storing instructions, which, when executed by the at least one hardware processor, cause the computer system to:
 receive an instruction for performing one or more operations on a plurality of retail stores; 
 apply a trained machine learning model to generate one or more suggested modifications to the received instruction; 
 generate one or more application programming interface (API) calls based on the generated one or more suggested modifications,
 wherein the one or more operations comprise opening the plurality of retail stores, closing the plurality of retail stores, opening tills in the plurality of retail stores, closing the tills in the plurality of retail stores, performing an audit of the plurality of retail stores, and/or generating reports for the plurality of retail stores; and 
 
 perform, using the one or more API calls, the one or more operations on the plurality of retail stores. 
 
 
     
     
       2. The computer system of  claim 1 , wherein the machine learning model is trained using customer information, user information, store information, social media information, and/or news information. 
     
     
       3. The computer system of  claim 1 , wherein the plurality of retail stores are associated with a telecommunications service provider. 
     
     
       4. The computer system of  claim 3 , wherein a source of the instruction is affiliated with the telecommunications service provider. 
     
     
       5. The computer system of  claim 1 , wherein the instruction is received via a voice bot. 
     
     
       6. The computer system of  claim 1 , wherein the one or more operations are performed at an execution time determined based on operating hours of the plurality of retail stores and/or current events information. 
     
     
       7. The computer system of  claim 1 , wherein the received instruction comprises information identifying the plurality of retail stores. 
     
     
       8. A computer-implemented method comprising:
 receiving an instruction for performing one or more operations on a plurality of retail stores; 
 applying a trained machine learning model to generate one or more suggested modifications to the received instruction; 
 generate one or more application programming interface (API) calls, 
 generating one or more application programming interface (API) calls based on the one or more suggested modifications,
 wherein the one or more operations comprise opening the plurality of retail stores, closing the plurality of retail stores, opening tills in the plurality of retail stores, closing the tills in the plurality of retail stores, performing an audit of the plurality of retail stores, and/or generating reports for the plurality of retail stores; and 
 
 performing, using the one or more API calls, the one or more operations on the plurality of retail stores. 
 
     
     
       9. The computer-implemented method of  claim 8 , wherein the instruction is received via a voice bot. 
     
     
       10. The computer-implemented method of  claim 8 , wherein the machine learning model is trained using customer information, user information, store information, social media information, and/or news information. 
     
     
       11. The computer-implemented method of  claim 8 , wherein the one or more operations are performed at an execution time determined based on operating hours of the plurality of retail stores and/or current events information. 
     
     
       12. The computer-implemented method of  claim 8 , wherein the received instruction comprises information identifying the plurality of retail stores. 
     
     
       13. The computer-implemented method of  claim 8 , wherein a source of the instruction is affiliated with the telecommunications service provider. 
     
     
       14. At least one non-transitory computer-readable storage medium storing instructions, which, when executed by at least one data processor of a system, cause the system to:
 receive an instruction for performing one or more operations on a plurality of retail stores; 
 apply a trained machine learning model to generate one or more suggested modifications to the received instruction; 
 generate one or more application programming interface (API) calls based on the generated one or more suggested modifications,
 wherein the one or more operations comprise opening the plurality of retail stores, closing the plurality of retail stores, opening tills in the plurality of retail stores, closing the tills in the plurality of retail stores, performing an audit of the plurality of retail stores, and/or generating reports for the plurality of retail stores; and 
 
 perform, using the one or more API calls, the one or more operations on the plurality of retail stores. 
 
     
     
       15. The non-transitory computer-readable storage medium of  claim 14 , wherein the plurality of retail stores are associated with a telecommunications service provider. 
     
     
       16. The non-transitory computer-readable storage medium of  claim 14 , wherein the instruction is received via a voice bot. 
     
     
       17. The non-transitory computer-readable storage medium of  claim 14 , wherein the machine learning model is trained using customer information, user information, store information, social media information, and/or news information. 
     
     
       18. The non-transitory computer-readable storage medium of  claim 14 , wherein the one or more operations are performed at an execution time determined based on operating hours of the plurality of retail stores and/or current events information.